NotesFAQContact Us
Collection
Advanced
Search Tips
Publication Date
In 20251
Education Level
Audience
Location
Laws, Policies, & Programs
Assessments and Surveys
What Works Clearinghouse Rating
Showing one result Save | Export
Peer reviewed Peer reviewed
Direct linkDirect link
David Broska; Michael Howes; Austin van Loon – Sociological Methods & Research, 2025
Large language models (LLMs) provide cost-effective but possibly inaccurate predictions of human behavior. Despite growing evidence that predicted and observed behavior are often not "interchangeable," there is limited guidance on using LLMs to obtain valid estimates of causal effects and other parameters. We argue that LLM predictions…
Descriptors: Artificial Intelligence, Observation, Prediction, Correlation